Deep Learning Methods in Classification of Myocardial Infarction by employing ECG Signals

K Manimekalai

doi:10.17485/ijst/v13i28.445

Abstract

Background/Objectives: To automatically classify and detect the Myocardial Infarction using ECG signals. Methods/Statistical analysis: Deep Learning algorithms Convolutional Neural Network(CNN), Long Short Term Memory(LSTM) and Enhanced Deep Neural Network(EDN) were implemented. The proposed model EDN, comprises the techniques CNN and LSTM. Vector operations like matrix multiplication and gradient decent were applied to large matrices of data that are executed in parallel with GPU support. Because of parallelism EDN faster the execution time of process. Findings: Proposed model EDN yields better accuracy (88.89%) than other state-of-art methods for PTB database. Novelty/Applications: The proposed classification algorithm for analyzing the ECG signals is obtained by comprising the Convolutional Neural Network(CNN)and Long short-term memory networks(LSTM). Also, it is identified that the novel classification technique based on deep learning decreases the misdiagnosis rate of MI. Keywords: Classification; CNN; deep learning; deep neural network; EDN; LSTM; Myocardial Infarction(MI)

Highlights

Myocardial infarction (MI) is a life threatening cardiovascular disease caused by inadequate blood supply in myocardial for human beings
In (13), a deep learning method is introduced by combining convolutional neural network (CNN) and recurrent neural network (RNN), and a multi-channel CNN and LSTM network architecture is established, preprocessed ECG signals are segmented, spatial features in the multi-channel convolution network are extracted, and the temporal characteristics through LSTM are acquired
This study proposed an algorithm EDN based on the CNN and LSTM algorithm

Summary

Introduction

Myocardial infarction (MI) is a life threatening cardiovascular disease caused by inadequate blood supply in myocardial for human beings. The classification model proposed in for MI detection(4) is based on Long Short Term Memory In this system the source 8-lead ECG signals are preprocessed and partitioned into heartbeat sequences. Being a part of signal processing domain, ECG signal feature extraction causes more implementation difficulties and which are reduced by applying deep learning techniques It uses CNN and LSTM for training the network. In (13), a deep learning method is introduced by combining CNN and RNN, and a multi-channel CNN and LSTM network architecture is established, preprocessed ECG signals are segmented, spatial features in the multi-channel convolution network are extracted, and the temporal characteristics through LSTM are acquired. To classify the Myocardial Infarction, this paper proposed a deep learning method combining CNN and LSTM

Materials and Methods

Experimental Results

Conclusion